qwen3-max
Qwen3 Max is a chat model developed by Qwen, capable of handling a wide range of tasks including function calling, JSON mode, reasoning, streaming, and text generation. It is genuinely best at tasks that require generating human-like text and code, as evidenced by its top 25% scores on the MMLU-Pro and LiveCodeBench benchmarks.
Input
Output
Context
258K
Max Output
66K
Parameters
1000B
Technical Specifications
Model TypeChat
Context Window258,048 tokens
Max Output Tokens65,536 tokens
Parameters1000B
Release DateSep 23, 2025
Training CutoffJun 1, 2025
Licenseproprietary
Open SourceNo
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
11.1%
HLE
76.4%
GPQA
38.3%
SciCode
84.1%
MMLU Pro
80.7
Math
26.4
Coding
76.7%
LiveCodeBench
24.0
Intelligence
59.3
Speed (tok/s)
2.0
TTFA (s)
2.0
TTFT (s)
Resources & Links
proprietary, Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.